Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5592 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.9091. Min Act: -0.1700
Data Index: 7357848 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.5653. Min Act: -0.1700
Data Index: 4962797 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.5340. Min Act: -0.1700
Data Index: 273704 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.5340. Min Act: -0.1700
Data Index: 2723255 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.5340. Min Act: -0.1700
Data Index: 4342748 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.5028. Min Act: -0.1700
Data Index: 3135231 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.4403. Min Act: -0.1700
Data Index: 6365176 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.5340. Min Act: -0.1700
Data Index: 1851375 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.4403. Min Act: -0.1700
Data Index: 6973838 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.4403. Min Act: -0.1700
Data Index: 2659761 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.4090. Min Act: -0.1700
Data Index: 6634943 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.3778. Min Act: -0.1700
Data Index: 2572291 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.3153. Min Act: -0.1700
Data Index: 3204381 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.3465. Min Act: -0.1700
Data Index: 6174064 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.3153. Min Act: -0.1700
Data Index: 2009908 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.3465. Min Act: -0.1700
Data Index: 8447135 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.3153. Min Act: -0.1700
Data Index: 5259484 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.2840. Min Act: -0.1700
Data Index: 7646113 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.2840. Min Act: -0.1700
Data Index: 1823076 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9091. Min Range: -4.9091
Max Act: 4.2840. Min Act: -0.1700
Data Index: 3542786 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19